Ada*_*bel 2 c# performance merge
using (StreamWriter writer = File.CreateText(FinishedFile))
{
int lineNum = 0;
while (lineNum < FilesLineCount.Min())
{
for (int i = 0; i <= FilesToMerge.Count() - 1; i++)
{
if (i != FilesToMerge.Count() - 1)
{
var CurrentFile = File.ReadLines(FilesToMerge[i]).Skip(lineNum).Take(1);
string CurrentLine = string.Join("", CurrentFile);
writer.Write(CurrentLine + ",");
}
else
{
var CurrentFile = File.ReadLines(FilesToMerge[i]).Skip(lineNum).Take(1);
string CurrentLine = string.Join("", CurrentFile);
writer.Write(CurrentLine + "\n");
}
}
lineNum++;
}
}
Run Code Online (Sandbox Code Playgroud)
我目前这样做的方式太慢了.我正在合并每个50k +行长的文件和不同数量的数据.
例如:文件1
1
2
3
4
档案2
4
3
2
1
我需要将它合并成第三个文件
文件3
1,4
2,3
3,2
4,1
P.S. 用户可以从任何位置选择任意数量的文件.
谢谢您的帮助.
由于循环Skip和Take循环,你的方法很慢.
您可以使用字典来收集所有行索引行:
string[] allFileLocationsToMerge = { "filepath1", "filepath2", "..." };
var mergedLists = new Dictionary<int, List<string>>();
foreach (string file in allFileLocationsToMerge)
{
string[] allLines = File.ReadAllLines(file);
for (int lineIndex = 0; lineIndex < allLines.Length; lineIndex++)
{
bool indexKnown = mergedLists.TryGetValue(lineIndex, out List<string> allLinesAtIndex);
if (!indexKnown)
allLinesAtIndex = new List<string>();
allLinesAtIndex.Add(allLines[lineIndex]);
mergedLists[lineIndex] = allLinesAtIndex;
}
}
IEnumerable<string> mergeLines = mergedLists.Values.Select(list => string.Join(",", list));
File.WriteAllLines("targetPath", mergeLines);
Run Code Online (Sandbox Code Playgroud)
| 归档时间: |
|
| 查看次数: |
76 次 |
| 最近记录: |